HR & RECRUITING
Monthly comp-band drift investigation with root-cause narrative and owner routing
Once a month an agent pulls all out-of-band offers and raises from BigQuery, investigates patterns by team, level, and geo, writes a root-cause narrative.
How it runs
The automated pipeline, trigger to output.
- TriggerOnce a month
- ActionPull trailing-month out-of-band actionsBigQuery
- LogicInvestigate patterns and draft root cause
- LogicGroup breaches by responsible HRBP
- OutputRoute each cluster to its HRBP in SlackSlack
What it does
This is the deeper monthly review that goes beyond flagging individual breaches. An agent queries BigQuery for every offer and raise that landed outside band over the trailing month, then investigates: which teams, levels, and geos concentrate the drift, whether breaches cluster under specific managers or roles, and how far the band is being stretched on average. It writes a plain-language root-cause narrative explaining what is driving the drift (a hot market for one role, a manager consistently over-leveling, a geo whose band is stale), then groups the breaches by responsible HR business partner and sends each HRBP their cluster in Slack with the cases and the recommended fix.
When to use it
Use it when you have recurring band drift and need to understand *why*, not just catch each instance. It fits HR leaders who want a monthly investigative readout that assigns ownership, rather than a flat exception list nobody acts on.
How it works
- 1A schedule trigger fires once a month.
- 2The agent queries BigQuery for all out-of-band offers and raises in the trailing period with their level, geo, team, and manager context.
- 3It analyzes the breaches for concentration patterns and drafts a root-cause narrative.
- 4It groups breaches by responsible HRBP and tailors a message per owner.
- 5Each HRBP receives their breach cluster and recommended action in Slack.
Set it up
What you configure once, before turning it on.
- 1Connect BigQueryDatasets, queries, schemas.
- 2Connect SlackChannels, DMs, threads, mentions.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More HR & Recruiting workflows
Assemble and send the debrief packet after the final interview
Triggered when a candidate's final interview ends on the calendar, it waits a short window for scorecards, compiles the aggregated packet to Google Drive.
New-Hire Credential Intake to Renewal Calendar Holds
When a new credential is added to the tracker, it validates the record, files the document.
Credential Renewal Evidence Verification Agent
When an employee replies with a renewed credential document, an agent reads the attachment, extracts the new expiry date and credential number.
Escalate Compliance-Blocking Credential Lapses to Managers
Each day it finds credentials that have already expired or expire within 48 hours and are flagged compliance-blocking.
Day-one readiness orchestrator across all onboarding owners
An agent-driven coordinator that, when a hire is launched, plans the full provisioning program across IT, Facilities, and Finance, opens the work in your tracker.
Loom intake to req-tracker row in Airtable
Transcribes a hiring manager's Loom intake, scores the brief for completeness, and either logs a ready req in Airtable or routes incomplete intakes to a follow-up Slack ping.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.